This repository holds the tutorials and helper code released with the AMASS paper (ICCV 2019); it is not under active development. On 2026-09-17 the dependencies were pinned so the notebooks match the installed human_body_prior: the notebooks' BodyModel calls (bm_fname, num_betas, num_dmpls, dmpl_fname) match the installed code and were exercised with a synthetic body model in tests/test_tutorial_calls.py, and each notebook's setup cells run in tests/test_notebook_prefixes.py; the tutorials were not run end to end with the licence-gated SMPL+H and SMPL-X models and AMASS data.

The data lives at https://amass.is.tue.mpg.de/. Questions about the dataset itself (contents, frame rates, ground planes, coordinate conventions, missing subjects, download access) go to the contact on that website, not to this repository.

AMASS is a large database of human motion unifying different optical marker-based motion capture datasets by representing them within a common framework and parameterization. AMASS is readily useful for animation, visualization, and generating training data for deep learning.

Here we provide tools and tutorials to use AMASS in your research projects. More specifically:

• Following the recommended splits of data by AMASS, we provide three non-overlapping train/validation/test splits.
• AMASS uses an extended version of SMPL+H with DMPLs. Here we show how to load different components and visualize a body model with AMASS data.
• AMASS is also compatible with SMPL and SMPL-X body models. We show how to use the body data from AMASS to animate these models.

• Installation
• Body Models
• Tutorials
• Citation
• License
• Contact

Requirements

• Python 3.11 or 3.12
• Human Body Prior, pinned by commit in requirements.txt and setup.py; it brings PyTorch
• body_visualizer and Pyrender for the visualisations in the notebooks

Clone this repo and run the following from the root folder:

pip install -r requirements.txt
pip install -e